跳到正文
研踪PaperTrail

论文库

检索计算机领域论文,按研究方向、作者或关键词筛选。

部分采集异常
正在读取账号与研究记录…

全站更新概况

+1352新增论文
+1083其中 AI 相关
+143已有论文修订
+94新增 AI 导读

arXiv 最近完成扫描:2026-11-19 06:59 · 全站最近入库:2026-11-19 15:04各信源进度 →

统计口径与数据新鲜度

统计 2026-11-18 16:08 — 2026-11-19 16:08(北京时间) · 点击数字查看对应简报;AI 相关包含在新增论文内。

最近完成检查:2026-11-19 06:59最近发现新增版本:2026-11-19 15:04库内论文最新更新时间:2026-11-19 02:59

每分钟刷新已保存的数据。空检查不代表采集异常;新收录可能包含历史论文。AI 导读按新增版本计数。

27,409 已收录论文22,787 AI 相关8,342 有修订112 HF 社区发现

浏览论文库

时间范围跟随排序:版本更新、本站收录或首次发表。最新收录可能包含历史论文。部分信源异常,查看状态 →

找到 7 篇论文 · 按版本更新时间排序上轮扫描起点 2026-11-19 06:57(北京时间)
新论文 · v1arXiv:2611.24864

NereidVLA: Learning to Understand and Navigate the Underwater World

Chenjie Zhao, Zhiliang Zhu, Quan Chen, Yuquan Xue, Xingxue Shi, Puyue Wang, Zhiqiang Zhao, Kangye Zheng 等 11 位作者

原文摘要

Underwater navigation requires translating visual spatial cues into motion, yet marine vision-language datasets rarely include paired robot trajectories. We present NereidVLA, a vision-language-action model that transfers marine spatial knowledge to language-conditioned 3D navigation. We first train Sea2Know on approximately two million marine examples to learn target grounding, spatial relations, and scene structure without paired robot-motion supervision. We then adapt it using expert trajectories executed under simulated underwater vehicle dynamics. Given RGB histories and a language instruction, NereidVLA predicts discrete motion tokens that decode into local 3D trajectories for closed-loop tracking. Evaluation combines an independent six-dimensional underwater navigation understanding benchmark with offline prediction and closed-loop navigation. Under matched navigation training and execution settings, marine spatial pretraining increases simulation success from 72.4% to 84.4%. Without fine-tuning on the real test environment, NereidVLA achieves 78.75% success in laboratory-pool robot trials, compared with 47.50% for InternVLA-N1. These results show that marine spatial supervision can support downstream motion learning and physical underwater navigation.

cs.CV · cs.RO

新论文 · v1arXiv:2611.22577

Semantic-Guided Geometric Decoding for Token-Efficient Visual Grounding

Zhaojie Chen, Junyan Yang, Le Yang, Qi Dang, Yucheng Huang, Qianyi Che, Zhaoqiang Chen, Xinqi Zhu 等 9 位作者

原文摘要

Multimodal large language models (MLLMs) provide a unified interface for language-conditioned visual perception. In pixel-to-sequence grounding, autoregressive coordinate generation requires multiple sequential decoding steps per box, increasing inference cost with the number of instances. Pixel-to-embedding methods reduce this overhead but lack explicit spatial encoding when using a shared special token. We introduce SemGeo, a token-efficient visual grounding framework that represents each instance with a single grid token for coarse localization. A geometric decoder reuses visual features and hidden states to recover precise discrete box coordinates in parallel. To train proposal generation and box localization together, we introduce Gaussian soft labels that encode coordinate distances during supervised fine-tuning (SFT). Reinforcement post-training further combines box-set rewards with coordinate supervision on model-generated proposals. This stage trains the language model and geometric decoder on their own predictions to mitigate the mismatch between teacher-forced training and inference. Across eight benchmarks spanning object detection, referring object detection, and document layout grounding, SemGeo achieves the highest F1@mIou among compared MLLMs on six benchmarks. It also delivers $2.07\times$ and $1.25\times$ the mean box-generation throughput of representative grounding baselines under vLLM and Transformers, respectively, while achieving higher accuracy in both comparisons.

cs.CV

版本更新 · v2arXiv:2610.36719

SAGE: Saliency-Aware Generalist Encoder with Multi-level Feature Enhancement for Visual Recognition

Junyu Chen, Yucheng Huang, Le Yang, Qi Dang, Xin Kong, Haifeng Huo, Qiang Zhao

原文摘要

Pretrained vision transformers (ViTs) have demonstrated strong transferability across visual recognition tasks. However, adapting a shared representation to diverse downstream tasks remains challenging, as different tasks demand varying levels of semantic abstraction and spatial precision. We present SAGE (Saliency-Aware Generalist Encoder), an encoder-side architecture that enhances pretrained ViT representations by integrating multi-depth features, register-token context, saliency-guided modulation, and aligned local views into a unified multi-scale feature pyramid. Evaluated with ViT-B and ViT-L backbones on six visual tasks across seven benchmarks, SAGE achieves 62.8 box AP, 55.3 mask AP, and 78.5 keypoint AP on COCO; 60.3 semantic segmentation mIoU and 44.9 instance segmentation AP on ADE20K; 94.76\% classification top-1 accuracy on TinyImageNet; and 81.10 oriented detection AP$_{50}$ on DIOR-R. Combined with a progressive two-stage training strategy, SAGE-L achieves the best performance among the selected reference methods in six of the seven benchmark settings, while remaining competitive on keypoint estimation against substantially larger models. Importantly, these tasks share the same SAGE encoder and multi-scale feature interface, while employing task-specific prediction heads. To the best of our knowledge, SAGE is the first publicly reported encoder to achieve highly competitive results on six visual tasks across seven benchmarks, demonstrating its generality and competitiveness.

cs.CV

新论文 · v1arXiv:2611.20507

VoxSAOR: Semantic-Aware Occupancy Robustification via Aleatoric Uncertainty Modeling

Mengfei Duan, Yuheng Zhang, Guoqiang Zhao, Yuanfan Zheng, Kailun Yang, Zhiyong Li

原文摘要

Vision-based 3D occupancy prediction provides a dense semantic representation of scenes for autonomous driving and embodied perception, yet remains vulnerable to occlusion, depth ambiguity, and projection errors that induce spatially varying reliability in voxel features. Existing methods typically map voxel representations to semantic predictions without explicitly modeling such observation-induced feature variations. To address this limitation, we propose VoxSAOR, a semantic-aware occupancy robustification framework that models aleatoric uncertainty through feature-space proxies. It first quantifies Local Semantic Consistency (LSC) to derive a voxel-wise structural stability prior and uses cross-view semantic consensus to filter unreliable semantic correspondences. Within each semantic category, spatially matched stable and ambiguous voxels form stable-to-ambiguous feature transitions, which are modeled by a class-conditional diagonal Gaussian distribution, capturing both feature displacement and dispersion. Guided by these proxy distributions, Aleatoric Regime Ensemble Learning (AREL) trains independently parameterized prediction heads using feature perturbations at progressively increasing scales, with perturbation strength modulated by structural reliability. At inference, proxy modeling and sampling are disabled, and all heads process the same observed features; their output probabilities are then averaged to produce a deterministic consensus prediction without requiring sampling. Experiments across multiple datasets and occupancy backbones demonstrate the effectiveness of VoxSAOR in improving semantic occupancy prediction, long-tail recognition, and predictive calibration. The source code will be made publicly available at https://github.com/MengfeiD/VoxSAOR.

cs.CV · cs.RO · eess.IV

新论文 · v1arXiv:2611.16818

Signed Dyadic Path Encoding for Efficient Non-Interactive Private Decision Tree Evaluation over TFHE

Xintong Song, Yiqiang Zhao, Qizhi Zhang, Yao Li, Jiaji He, Fei Zhao

原文摘要

Private decision-tree evaluation lets a server classify a client's encrypted query without learning the input. In the non-interactive, path-based setting over TFHE, the server returns a single encrypted prediction by aggregating per-path comparison outcomes, and the standard per-leaf formulation pays one programmable bootstrap (PBS) per leaf, which dominates the cost. We propose a signed dyadic path-sum encoding that nearly halves this cost: each internal node receives a signed dyadic label so that every root-to-leaf path accumulates a distinct integer sum, which lets the two children of a leaf-parent be packed into a single test polynomial and resolved by one PBS, reducing the PBS count from the number of leaves to the number of leaf-parents. We formalize the distinct-sum property and prove that the dyadic labeling is the range-minimal encoding satisfying it, and its half-symmetric signed form is magnitude-optimal, tightening the comparison-stage noise bound at fixed parameters. We derive the two conditions under which the encrypted evaluation returns the exact prediction and instantiate parameters with per-inference failure below $2^{-64}$ at 128-bit security. We show that the ring degree grows linearly with the consumed plaintext range, which confines the profitable regime to depths $\leq 4$, where our method stays faster even when each scheme runs at its own cost-optimal parameters. We further extend the encoding to gradient-boosted ensembles. On standard UCI benchmarks at depths 1-4, our method reduces single-tree latency by $1.51\times$-$1.92\times$ and ensemble latency by $2\times$, without accuracy loss, while preserving the compact, non-interactive response.

cs.CR

新论文 · v1arXiv:2611.06040

USI-Brain: Enhancing Underwater Spatial Intelligence via Spatial Data-Driven Vision-Language Modeling

Zhiliang Zhu, Zhiqiang Zhao, Xie'an Jiang, Yingxin Lai, Kangye Zheng, Dawei Zhao

原文摘要

Underwater spatial reasoning depends on object boundaries and geometric cues that are obscured by scattering, color distortion, and low visibility. Existing underwater resources capture these cues through images, annotations, and depth maps, but provide fragmented supervision for vision-language models. We present a spatial data engine that connects visual appearance with object-level geometry through enhancement, 2D and geometry-assisted question generation, and expert filtering. It produces 4.27M QA pairs across five capability groups. We use this corpus to train USI-Brain and introduce an Underwater Prior-guided Rectifier (UPR) that applies gated corrections to visual features. USI-Bench evaluates the resulting capabilities with 6,525 held-out QA pairs. On its 15 task metrics, USI-Brain and USI-Brain + UPR improve over Qwen3-VL-8B-Instruct by 5.76 and 7.63 points on average, respectively, using signed differences on 100-point scales. Ablations show that geometry-assisted supervision improves depth and ordering by 4.8 and 6.1 points with UPR disabled, while UPR adds 18.0 points in scene description under matched training data. Both variants use raw images at evaluation. Across NautData, UWBench, and MarineEval, USI-Brain achieves the best or joint-best score on 28 of 32 metrics. Model weights and USI-Bench will be released at https://github.com/SKY-Zhu-91/USI-Brain.

cs.CV

首次观测 · 记录 #1ACL Anthology · ACL 2026:acl:2026.acl-long.4ACL Anthology · ACL 2026

Your Inference Request Will Become a Black Box: Confidential Inference for Cloud-based Large Language Models

Chung-ju Huang, Huiqiang Zhao, Yuanpeng He Peking University, Lijian Li University of Macau, Wenpin Jiao Peking University, Zhi Jin Peking University, Peixuan Chen, Leye Wang Peking University

原文摘要

The increasing reliance on cloud-hosted Large Language Models (LLMs) exposes sensitive client data, such as prompts and responses, to potential privacy breaches by service providers.Existing approaches fail to ensure privacy, maintain model performance, and preserve computational efficiency simultaneously.To address this challenge, we propose Talaria, a confidential inference framework that partitions the LLM pipeline between a client-verified Confidential Virtual Machine (CVM) and the public cloud to protect client data without compromising the cloud’s model intellectual property or inference quality.The interaction between the CVM and the cloud is secured by our Reversible Masked Outsourcing (ReMO) protocol, which uses a hybrid masking technique to reversibly obscure intermediate data before outsourcing computations.Extensive evaluations show that Talaria can defend against state-of-the-art token inference attacks, reducing token reconstruction accuracy from over 97.5% to an average of 1.34%, all while being a lossless mechanism that guarantees output identical to the original model without significantly decreasing efficiency and scalability.To the best of our knowledge, this is the first work that ensures clients’ prompts and responses remain inaccessible to the cloud, while also preserving model privacy, performance, and efficiency.

cs.CL

Proceedings of the 64th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers) · 2026 · 正式发表